INDEX

Explanations

mathematical terms and expressions related to analysis and transformations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

set

-0.45

↵↵

-0.44

’

-0.44

hr

-0.42

per

-0.41

te

-0.40

</b>

-0.40

ans

-0.40

et

-0.39

 trust

-0.39

POSITIVE LOGITS

AndEndTag

1.04

styleType

0.97

endphp

0.96

 kasarigan

0.92

 betweenstory

0.91

-------------</

0.87

 defaultstate

0.87

 propOrder

0.86

PerformLayout

0.86

mybatisplus

0.86

Activations Density 2.259%

mathematical terms and expressions related to analysis and transformations

No Comments

No Known Activations